kazukit-dev/dotfiles
kazukit's dotfiles
ARCHETYPE
Orchestrator
A bench of specialised subagents. The main agent mostly delegates.
Copy this rig
# review before running: this installs third-party code $ claude mcp add nixos -- uvx mcp-nixos $ npx degit kazukit-dev/dotfiles/.claude ./rig-dotfiles # inspect, then merge into .claude/
MCP servers are added to Claude Code at local scope; env vars are shown as YOUR_… placeholders — we never store values. Files are fetched with degit into a separate folder so you can review before merging.
$ claude mcp add nixos -- uvx mcp-nixos $ npx degit kazukit-dev/dotfiles/agents/skills/code-review .claude/skills/code-review $ npx degit kazukit-dev/dotfiles/agents/skills/commit .claude/skills/commit $ npx degit kazukit-dev/dotfiles/agents/skills/tdd .claude/skills/tdd $ npx degit kazukit-dev/dotfiles/agents/skills/testing .claude/skills/testing
$ curl -fsSL --create-dirs -o .claude/agents/SKILL.md https://raw.githubusercontent.com/kazukit-dev/dotfiles/main/agents/skills/code-review/SKILL.md $ curl -fsSL --create-dirs -o .claude/agents/SKILL.md https://raw.githubusercontent.com/kazukit-dev/dotfiles/main/agents/skills/commit/SKILL.md $ curl -fsSL --create-dirs -o .claude/agents/SKILL.md https://raw.githubusercontent.com/kazukit-dev/dotfiles/main/agents/skills/tdd/SKILL.md $ curl -fsSL --create-dirs -o .claude/agents/SKILL.md https://raw.githubusercontent.com/kazukit-dev/dotfiles/main/agents/skills/testing/SKILL.md $ curl -fsSL --create-dirs -o .claude/agents/integration-testing.md https://raw.githubusercontent.com/kazukit-<redacted>-testing.md $ curl -fsSL --create-dirs -o .claude/agents/unit-testing.md https://raw.githubusercontent.com/kazukit-<redacted>-testing.md
This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 7,204 rigs:
{
"permissions": {
"deny": [
"Read(./.env)",
"Read(**/.env)",
"Read(~/.ssh/**)",
"Bash(rm -rf *)",
"Read(**/*.pem)",
"Bash(rm -rf /)",
"Bash(git push --force:*)",
"Bash(sudo *)",
"Read(.env)",
"Bash(rm -rf /*)",
"Read(./.env.*)",
"Read(~/.aws/**)",
"Bash(git push --force*)",
"Bash(rm -rf:*)",
"Read(**/*.key)",
"Read(**/.env.*)",
"Bash(sudo:*)",
"Bash(git reset --hard*)",
"Bash(git reset --hard:*)",
"Read(.env.*)"
],
"ask": [
"Bash(git push:*)",
"Bash(git push *)",
"Bash(git commit:*)",
"Bash(rm *)",
"Bash(rm:*)",
"Bash(git rebase *)",
"Bash(wget *)",
"Bash(npm publish:*)",
"Bash(git commit *)",
"Bash(gh pr merge *)"
]
}
} MCP servers (1)
| server | source | est. tokens |
|---|---|---|
| mcp-nixos · "nixos" | pypi | 2.5k |
Skills (4)
Subagents (6)
| code-review | コードレビュー用の汎用スキル。lint・formatter・型チェックを実際に実行したうえで、正しさ・根本原因・エラーハンドリング・設計・セキュリティ・テスト・依存関係・可読性の8観点で、severity付きの指摘を出す。コードレビュー、PRレビュー、diffの確認、「このコード見て」「レビューして」「この修正で大丈夫?」といった依頼、AIエージェントが書いたコードや修正の妥当性確認、マージ前チェ |
| commit | Analyze staged changes and create a detailed git commit message in English |
| tdd | |- |
| testing | |- |
| integration-testing | — |
| unit-testing | — |
Hooks (1)
| event | matcher | runs |
|---|---|---|
| PostToolUse | Write|Edit | nix fmt |
Similar rigs
pravindurgani/claude-code-multipane-iterm2
Stop your AI agent from reviewing its own code — 4-pane iTerm2 setup with role-locked Claude Code sessions. Step-by-step guide included.
Minimalist 1.0k tok ·
edenfunf/promptc
Measure worst-case skill-context exposure in your Claude Code setup.
Pragmatist 136 tok ·
csvenke/dotfiles
❄️ My dotfiles
Pragmatist 4.0k tok ·
ShadyManu/ai-config
Define your AI coding configuration once under `.ai/`, and keep Claude Code, OpenAI Codex, GitHub Copilot and OpenCode synchronized from it.
Pragmatist 356 tok ·